Knowledge catalogue
arXiv:2606.27269v1 Announce Type: cross Abstract: Reliably quantifying predictive uncertainty is difficult for complex, high-dimensional, or misspecified models. Both fully Bayesian and bootstrap resa
arXiv:2606.26863v1 Announce Type: new Abstract: Rolling shutter (RS) cameras equip virtually all consumer devices, yet RS-aware relative pose estimation has remained impractical: the state-of-the-art
arXiv:2606.26997v1 Announce Type: cross Abstract: Large language model (LLM) post-training for reasoning increasingly relies on reinforcement learning with verifiable rewards (RLVR), where models lear
arXiv:2606.27332v1 Announce Type: new Abstract: Moving an object in a single image requires geometry-consistent spatial rearrangement, including handling occlusions, revealing previously unseen region
arXiv:2603.30014v2 Announce Type: replace-cross Abstract: The Production and Distributed Analysis (PanDA) system, originally developed for the ATLAS experiment at the CERN Large Hadron Collider (LHC),
arXiv:2606.26341v1 Announce Type: new Abstract: Many robotics problems, including trajectory optimization, inverse kinematics, and contact-rich motion planning, reduce to nonlinear programs (NLPs). Ma
arXiv:2601.04390v2 Announce Type: replace Abstract: High-quality methodology figures are central to scientific communication, yet they remain difficult and time-consuming to create. Such figures must
arXiv:2606.27027v1 Announce Type: cross Abstract: With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become fo
arXiv:2606.18430v2 Announce Type: replace Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals
arXiv:2603.10446v4 Announce Type: replace Abstract: Sign Language Production (SLP) faces a fundamental trade-off: direct text-to-pose models suffer from regression-to-the-mean effects, while dictionar
arXiv:2606.26669v1 Announce Type: new Abstract: Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces. Prior work has explo
arXiv:2606.26466v1 Announce Type: new Abstract: Multilingual large language models often produce inconsistent reasoning and answers for semantically equivalent prompts in different languages. Prior wo
arXiv:2606.26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet th
arXiv:2606.26800v1 Announce Type: new Abstract: Real-world robotic manipulation demands spatial grounding, task-aware reasoning, and precise control. Learning such capabilities becomes particularly ch
arXiv:2606.26387v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. De
arXiv:2601.20381v3 Announce Type: replace Abstract: Visual foundation models provide strong perceptual features for robotics, but their dense representations lack explicit object-level structure, limi
arXiv:2606.12808v3 Announce Type: replace-cross Abstract: Adaptive Hamiltonian learning is central to calibrating and characterizing quantum devices. In an adaptive controller, choosing the next exper
arXiv:2606.26511v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) gives agents access to accumulated knowledge, but has no model of time. When a fact changes (e.g., a function is
arXiv:2606.26963v1 Announce Type: new Abstract: Organizing knowledge from diverse text sources into interpretable hierarchies is crucial for tasks such as policy analysis, innovation monitoring, and e
arXiv:2606.26529v1 Announce Type: cross Abstract: AI safety is evaluated by how reliably a model detects the hazards it is told to find, yet accidents often arise from the hazard no one specified. We
arXiv:2606.26118v1 Announce Type: cross Abstract: We work towards measuring both AI adoption and the capability of AI to perform discrete labor tasks across various occupations. To measure adoption, w
The strongest models are gated and access is granted only to a select few. Hermes Agent now exposes MoA presets as virtual models, giving you capabilities beyond the publicly available frontier: 8% hi
arXiv:2606.26300v1 Announce Type: new Abstract: A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foun
arXiv:2606.27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of
arXiv:2603.01195v2 Announce Type: replace-cross Abstract: The effectiveness of multimodal instruction tuning depends not only on dataset scale, but critically on whether training samples genuinely req
arXiv:2601.11906v2 Announce Type: replace Abstract: Crop monitoring is essential for precision agriculture, but current systems lack high-level reasoning. We introduce a novel, modular framework that
arXiv:2606.27215v1 Announce Type: new Abstract: Deep learning models have achieved impressive performance across various fields but remain vulnerable to adversarial inputs, particularly in NLP, where
arXiv:2602.08995v2 Announce Type: replace Abstract: Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from th
arXiv:2606.27359v1 Announce Type: cross Abstract: Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, ei
arXiv:2606.14668v3 Announce Type: replace Abstract: Knowledge editing systems must update selected facts while preserving nearby but irrelevant behavior. This paper studies this problem in a memory-as
arXiv:2603.19964v3 Announce Type: replace Abstract: High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models ar
arXiv:2606.25886v1 Announce Type: cross Abstract: Existing texture datasets for tactile sensing primarily consist of sensor readings from a specific sensor interacting with available surfaces/objects
arXiv:2606.25200v1 Announce Type: new Abstract: The accelerated digitalization of renewable energy smart grids through IoT sensors, AMI, and SCADA systems has significantly expanded the attack surface
arXiv:2507.06457v2 Announce Type: replace Abstract: Transformers face quadratic complexity and memory issues with long sequences, prompting the adoption of linear attention mechanisms using fixed-size
arXiv:2606.22902v2 Announce Type: replace Abstract: Real-world users typically have access to multiple Large Language Models (LLMs) from different providers, and these LLMs often excel at distinct dom
arXiv:2606.25879v1 Announce Type: cross Abstract: Computational reproducibility remains difficult despite being central to scientific research. In this paper, we show how the international FABRIC test
arXiv:2606.25503v1 Announce Type: cross Abstract: Reliable depth perception is critical for robotic manipulation, especially for non-Lambertian objects such as transparent or highly specular surfaces,
arXiv:2606.24995v1 Announce Type: new Abstract: Tabular foundation models (TFMs) achieve strong performance on microbiome abundance data, yet their robustness under realistic distribution shift remain
arXiv:2606.25084v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have redefined visual understanding by combining vision encoders with large-scale language models. This unified
arXiv:2507.07920v2 Announce Type: replace-cross Abstract: Cerebrovascular research heavily relies on quantitative analysis of intracranial arteries from time-of-flight magnetic resonance angiography,
arXiv:2603.11606v2 Announce Type: replace Abstract: Building high-fidelity digital twins of articulated objects from visual data remains a central challenge. Existing approaches depend on multi-view c
arXiv:2511.11421v2 Announce Type: replace Abstract: Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models s
arXiv:2606.25400v1 Announce Type: new Abstract: Brain-Computer Interfaces (BCIs) and brain signal understanding are pivotal for clinical health and next-generation interactions. Despite this significa
arXiv:2606.25761v1 Announce Type: new Abstract: When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consens
arXiv:2606.14581v2 Announce Type: replace Abstract: Granting LLMs direct control over costly, irreversible scientific experiments leads to unsafe exploration and unstable performance, but discarding L
arXiv:2606.25273v1 Announce Type: new Abstract: Zero-shot 3D anomaly detection is essential for industrial quality inspection, where labeled anomaly samples are scarce. Meanwhile, existing methods lac
arXiv:2604.03314v2 Announce Type: replace-cross Abstract: Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures compos
arXiv:2603.25645v2 Announce Type: replace-cross Abstract: Early screening via colonoscopy is critical for colon cancer prevention, yet developing robust AI systems for this domain is hindered by the l
arXiv:2606.25293v1 Announce Type: new Abstract: Positional encodings (PEs) are essential for Transformers. Yet designing effective PEs for non-Euclidean graphs remains challenging. Such encodings shou
arXiv:2602.01472v2 Announce Type: replace Abstract: Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inf
arXiv:2606.24983v1 Announce Type: cross Abstract: Implicit solvent machine learning potentials (MLPs) offer a powerful route to bridging the gap between accuracy and efficiency in molecular simulation
arXiv:2606.24956v1 Announce Type: new Abstract: Spectral graph neural networks (GNNs) interpret message passing as frequency-selective filtering. While low-order spectral filters are efficient, their
arXiv:2606.25332v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptibl
arXiv:2606.25360v1 Announce Type: new Abstract: While end-to-end Vision-Language-Action (VLA) models show promise in robotic manipulation, their monolithic paradigm inherently couples semantic reasoni
arXiv:2606.25769v1 Announce Type: new Abstract: In many prediction problems in medical applications, target labels exhibit an inherent ordinal structure, where class ordering reflects clinically meani
arXiv:2606.25939v1 Announce Type: new Abstract: Demonstration augmentation is proposed for cost-efficient data acquisition, but existing methods are fundamentally limited in deformable manipulation du
arXiv:2606.24898v1 Announce Type: new Abstract: Looped language models turn hidden states into runtime state: each state is decoded for prediction and fed back into future computation. This creates a
arXiv:2606.26036v1 Announce Type: new Abstract: Training-time data poisoning during fine-tuning poses a significant threat to large language models (LLMs) deployed for abstractive text summarization,
arXiv:2511.12100v2 Announce Type: replace Abstract: In current visual model training, models often rely on only limited sufficient causes for their predictions, which makes them sensitive to distribut
arXiv:2606.25546v1 Announce Type: new Abstract: Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet e